{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PURKXMCYXDHM2J3ANXUD2R6SFP","short_pith_number":"pith:PURKXMCY","schema_version":"1.0","canonical_sha256":"7d22abb058b8cecd27606de83d47d22bccd734f4b8cc120dc08e8c4e73e74db8","source":{"kind":"arxiv","id":"2501.02045","version":1},"attestation_state":"computed","paper":{"title":"METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"q-bio.GN","authors_text":"Jason Wiemels, Jeff Kaufman, Johannes Hagemann, Ollie Liu, Sami Jaghouar, Shangshang Wang, Willie Neiswanger","submitted_at":"2025-01-03T18:44:43Z","abstract_excerpt":"We pretrain METAGENE-1, a 7-billion-parameter autoregressive transformer model, which we refer to as a metagenomic foundation model, on a novel corpus of diverse metagenomic DNA and RNA sequences comprising over 1.5 trillion base pairs. This dataset is sourced from a large collection of human wastewater samples, processed and sequenced using deep metagenomic (next-generation) sequencing methods. Unlike genomic models that focus on individual genomes or curated sets of specific species, the aim of METAGENE-1 is to capture the full distribution of genomic information present within this wastewat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.02045","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-01-03T18:44:43Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"c98abbec4ae7ca782495aa8bee996d0c33246a6e3df4495622186a710878ec2b","abstract_canon_sha256":"f54b3354ee05ed6f3ff0bf8694f7e470cc397578948bb366643585e916de5b5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:00.896835Z","signature_b64":"g7CN0NHG5BaJ99X+0cD0C7ClONMvMsSqXxLLwzwppsWLlJh54GnY4bjM/vPJ1bAsFTYOrJ+/QaG5iyq5HiFBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d22abb058b8cecd27606de83d47d22bccd734f4b8cc120dc08e8c4e73e74db8","last_reissued_at":"2026-07-05T09:57:00.896408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:00.896408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"q-bio.GN","authors_text":"Jason Wiemels, Jeff Kaufman, Johannes Hagemann, Ollie Liu, Sami Jaghouar, Shangshang Wang, Willie Neiswanger","submitted_at":"2025-01-03T18:44:43Z","abstract_excerpt":"We pretrain METAGENE-1, a 7-billion-parameter autoregressive transformer model, which we refer to as a metagenomic foundation model, on a novel corpus of diverse metagenomic DNA and RNA sequences comprising over 1.5 trillion base pairs. This dataset is sourced from a large collection of human wastewater samples, processed and sequenced using deep metagenomic (next-generation) sequencing methods. Unlike genomic models that focus on individual genomes or curated sets of specific species, the aim of METAGENE-1 is to capture the full distribution of genomic information present within this wastewat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02045","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.02045/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.02045","created_at":"2026-07-05T09:57:00.896470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.02045v1","created_at":"2026-07-05T09:57:00.896470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02045","created_at":"2026-07-05T09:57:00.896470+00:00"},{"alias_kind":"pith_short_12","alias_value":"PURKXMCYXDHM","created_at":"2026-07-05T09:57:00.896470+00:00"},{"alias_kind":"pith_short_16","alias_value":"PURKXMCYXDHM2J3A","created_at":"2026-07-05T09:57:00.896470+00:00"},{"alias_kind":"pith_short_8","alias_value":"PURKXMCY","created_at":"2026-07-05T09:57:00.896470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17333","citing_title":"AutomataGPT: Forecasting and Ruleset Inference for Two-Dimensional Cellular Automata","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PURKXMCYXDHM2J3ANXUD2R6SFP","json":"https://pith.science/pith/PURKXMCYXDHM2J3ANXUD2R6SFP.json","graph_json":"https://pith.science/api/pith-number/PURKXMCYXDHM2J3ANXUD2R6SFP/graph.json","events_json":"https://pith.science/api/pith-number/PURKXMCYXDHM2J3ANXUD2R6SFP/events.json","paper":"https://pith.science/paper/PURKXMCY"},"agent_actions":{"view_html":"https://pith.science/pith/PURKXMCYXDHM2J3ANXUD2R6SFP","download_json":"https://pith.science/pith/PURKXMCYXDHM2J3ANXUD2R6SFP.json","view_paper":"https://pith.science/paper/PURKXMCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.02045&json=true","fetch_graph":"https://pith.science/api/pith-number/PURKXMCYXDHM2J3ANXUD2R6SFP/graph.json","fetch_events":"https://pith.science/api/pith-number/PURKXMCYXDHM2J3ANXUD2R6SFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PURKXMCYXDHM2J3ANXUD2R6SFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PURKXMCYXDHM2J3ANXUD2R6SFP/action/storage_attestation","attest_author":"https://pith.science/pith/PURKXMCYXDHM2J3ANXUD2R6SFP/action/author_attestation","sign_citation":"https://pith.science/pith/PURKXMCYXDHM2J3ANXUD2R6SFP/action/citation_signature","submit_replication":"https://pith.science/pith/PURKXMCYXDHM2J3ANXUD2R6SFP/action/replication_record"}},"created_at":"2026-07-05T09:57:00.896470+00:00","updated_at":"2026-07-05T09:57:00.896470+00:00"}